Custom AI

Automated Evaluations

Content is machine translated from English by Phrase Language AI.

Automated evaluations are provided for every MT model. Click on a model name or the ellipsis ellipses.png in the More column to view them.

Phrase Custom AI offers rich data and advanced visual support designed to provide a deeper understanding of custom MT model quality:

  • The Overview tab supports intuitive visualizations, including:

    • A bar chart to compare the performance of generic versus custom MT models across four key metrics.

    • A pie chart detailing the quality categorization of each segment within the evaluation set:

      • Significantly improved

      • Improved

      • Insignificant changes

      • Worse

      • Significantly worse

  • The Visualizations tab features a scatter plot chart, offering a detailed comparison between custom and baseline engine MT quality on a segment-by-segment basis. Hover over each point to access valuable metadata such as:

    • Source

    • Reference

    • Generic engine translation

    • Customized engine translation

    • MT score

    • Quality category

  • The Sample preview tab presents a segment sample preview from the evaluation set, displaying essential information including:

    • Source

    • Reference

    • Generic engine translation

    • Customized engine translation

    • MT score

    • Quality category

Was this article helpful?

Sorry about that! In what way was it not helpful?

The article didn’t address my problem.
I couldn’t understand the article.
The feature doesn’t do what I need.
Other reason.

Note that feedback is provided anonymously so we aren't able to reply to questions.
If you'd like to ask a question, submit a request to our Support team.
Thank you for your feedback.